© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 858
    Prev
    Next
    INDEX
    Explanations

    he

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Referanser
    -0.61
    han
    -0.60
    élite
    -0.59
     initState
    -0.55
    المناصب
    -0.54
     Italijanski
    -0.54
    tizo
    -0.53
     pedest
    -0.53
    hane
    -0.53
    beams
    -0.52
    POSITIVE LOGITS
    ⓧ
    0.62
     Normdatei
    0.56
    MarshalTo
    0.53
    findpost
    0.53
    RunAsync
    0.52
    IUrlHelper
    0.51
     dage
    0.51
     Lagi
    0.50
     dags
    0.48
    +#+#
    0.47
    Activations Density 0.017%

    No Known Activations